Paper Citation Record · LEDGER

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems

As of 15 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2605.24863.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2605.24863 v2

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T00:13:50.278588Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact11
verified fuzzy0
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c129b68b-e6cf-48e0-aacf-82718ba827d8 · outbound

This paper cites AFT: An exemplar-free class incremental learning method for en- vironmental sound classification.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems AFT: An exemplar-free class incremental learning method for en- vironmental sound classification

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-30T00:13:50.278588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25168432-d4f4-4f79-8e6b-ec52247ee8bf · outbound

This paper cites Qwen2-Audio Technical Report.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Qwen2-Audio Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-30T00:14:04.006152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 090366d2-51c7-47d0-9a72-af0a132e54ac · outbound

This paper cites Closing the gap between text and speech under- standing in llms.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Closing the gap between text and speech under- standing in llms

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T00:14:04.013937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d8ca090e-337d-454d-ace7-38ab1674b17f · outbound

This paper cites De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., and Tuytelaars, T.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., and Tuytelaars, T

Reference 4

Resolution: verified exact; doi, observed 2026-06-30T00:14:03.860450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ce94efe3-23ec-4057-9b9d-82c2a6c70512 · outbound

This paper cites CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:14:04.041949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f92579aa-69b9-48d0-8221-38b0b2c2eee8 · outbound

This paper cites Domain Expan- sion in DNN-Based Acoustic Models for Robust Speech Recognition.2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Domain Expan- sion in DNN-Based Acoustic Models for Robust Speech Recognition.2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-30T00:13:50.278588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22bf6741-a9d7-4308-909d-fd4c133a05d0 · outbound

This paper cites Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:14:04.020962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b43e3b1b-912b-4041-bc5c-6c04571102cc · outbound

This paper cites doi: 10.1073/pnas.1611835114.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems doi: 10.1073/pnas.1611835114

Reference 8

Resolution: metadata mismatch; doi, observed 2026-06-30T00:14:03.857071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T15:08:18.195064+00:00.

Observation 1a3acc8e-2fce-460b-8468-745930089010 · outbound

This paper cites Weinberger , editor =.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Weinberger , editor =

Reference 9

Resolution: verified exact; doi, observed 2026-06-30T00:14:03.853165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d3f6325f-5fc5-4917-9a72-97809fbae33f · outbound

This paper cites A Parameter-efficient Language Extension Framework for Multilingual ASR.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems A Parameter-efficient Language Extension Framework for Multilingual ASR

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:14:04.017247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 749c9464-112a-4478-b543-8af0aa6a1ce7 · outbound

This paper cites and Xiao, Y.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems and Xiao, Y

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-30T00:13:50.278588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3362d18-bfaf-4b26-9716-da4c314b9e6a · outbound

This paper cites A Practitioner's Guide to Continual Multimodal Pretraining.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems A Practitioner's Guide to Continual Multimodal Pretraining

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:14:04.027840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c318cf85-9af5-4ef0-9fa1-ef90167007e7 · outbound

This paper cites Closing the Modality Reasoning Gap for Speech Large Language Models.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Closing the Modality Reasoning Gap for Speech Large Language Models

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-06-30T00:14:04.038250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e8281b3c-0ff3-44a4-925c-32bd97ae5118 · outbound

This paper cites Cross-modal knowledge distillation for speech large language models.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Cross-modal knowledge distillation for speech large language models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:14:04.009657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5418468f-b99b-4f76-ba52-c2de851dd59a · outbound

This paper cites Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:14:04.035066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 05f3fa04-a993-43e4-977c-7447cd357754 · outbound

This paper cites S., and Lee, H.-y.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems S., and Lee, H.-y

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-30T00:13:50.278588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5292192d-5652-4449-bd9b-310a82a1f76d · outbound

This paper cites To- wards Lifelong Learning of Multilingual Text-to-Speech Synthesis.ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems To- wards Lifelong Learning of Multilingual Text-to-Speech Synthesis.ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-30T00:13:50.278588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84305c98-a1c1-4164-bd2c-6870348b1e64 · outbound

This paper cites Continual Learning with Embedding Layer Surgery and Task-wise Beam Search using Whisper.

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems Continual Learning with Embedding Layer Surgery and Task-wise Beam Search using Whisper

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:14:04.031585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.